public void TestDiscoverSimpleParaTCs2()
{
string fileName = TESTFILE_DIR + "TestDiscoverParaStyles2.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttTC = docText.GetUniqueTextType(ContentType.TrackChange);
Assert.IsNotNull(ttTC, "we unexpectedly found no track changes");
Assert.AreEqual(5, ttTC.Count, "Expected to get 5 separate track change items");
Assert.AreEqual("Style", ttTC.Nodes[0].GetInfo("Type")[0].value);
Assert.AreEqual("Workshare", ttTC.Nodes[0].GetInfo("Author")[0].value);
Assert.AreEqual("Paragraph 1\r", ttTC.Nodes[0].GetInfo("Content")[0].value);
Assert.AreEqual("Paragraph Property", ttTC.Nodes[1].GetInfo("Type")[0].value);
Assert.AreEqual("Workshare", ttTC.Nodes[1].GetInfo("Author")[0].value);
Assert.AreEqual("Paragraph 2\r", ttTC.Nodes[1].GetInfo("Content")[0].value);
Assert.AreEqual("ListNumber", ttTC.Nodes[2].GetInfo("Type")[0].value);
Assert.AreEqual("Workshare", ttTC.Nodes[2].GetInfo("Author")[0].value);
Assert.AreEqual("Paragraph 3\r", ttTC.Nodes[2].GetInfo("Content")[0].value);
Assert.AreEqual("Paragraph Property", ttTC.Nodes[3].GetInfo("Type")[0].value);
Assert.AreEqual("Workshare", ttTC.Nodes[3].GetInfo("Author")[0].value);
Assert.AreEqual("Paragraph 4\r", ttTC.Nodes[3].GetInfo("Content")[0].value);
Assert.AreEqual("ListNumber", ttTC.Nodes[4].GetInfo("Type")[0].value);
Assert.AreEqual("Workshare", ttTC.Nodes[4].GetInfo("Author")[0].value);
Assert.AreEqual("Paragraph 5\r", ttTC.Nodes[4].GetInfo("Content")[0].value);
}
protected void TestCleanTextTypeFromDocument(string fileName, ContentType contentType, string[] textThatShouldntBeCleaned)
{
fileName = TESTFILE_DIR + fileName;
string outFileName = fileName + "_cleaned.doc";
File.Copy(fileName, outFileName, true);
using (Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(outFileName, true))
{
docReader.Clean(BuildContentTypeList(contentType));
}
using (WordDocumentReader docReader2 = new WordDocumentReader(outFileName, false))
{
DocumentText dt = docReader2.Read();
IAbstractTextType tt = dt.GetUniqueTextType(contentType);
IAbstractTextType ttHid = dt.GetUniqueTextType(ContentType.HiddenText);
if (tt == null && ttHid == null)
{
CheckHaventCleanedTooMuch(dt.GetUniqueTextType(ContentType.Paragraph), textThatShouldntBeCleaned);
return;
}
if (tt != null)
Assert.AreEqual(0, tt.Nodes.Count, "Expected all the items of type " + contentType.ToString() + " to have been cleaned");
if (ttHid != null)
Assert.AreEqual(0, ttHid.Nodes.Count, "Expected no significant hidden text to show up");
}
}
private void TestCleanTCsFromDocument(string fileName, bool checkHiddenText)
{
string outFileName = fileName + "_cleaned.doc";
File.Copy(fileName, outFileName, true);
using (Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(outFileName, true))
{
docReader.Clean(BuildContentTypeList(ContentType.TrackChange));
}
using (WordDocumentReader docReader2 = new WordDocumentReader(outFileName, false))
{
DocumentText dt = docReader2.Read();
IAbstractTextType tt = dt.GetUniqueTextType(ContentType.TrackChange);
IAbstractTextType ttHid = dt.GetUniqueTextType(ContentType.HiddenText);
if (tt == null && ttHid == null)
return;
if (tt != null)
Assert.AreEqual(0, tt.Nodes.Count, "Expected all the track changes to have been cleaned");
if (checkHiddenText)
{
if (ttHid != null)
Assert.AreEqual(0, ttHid.Nodes.Count, "Expected no significant hidden text to show up");
}
}
}
public override void Execute(WorkItem workItem)
{
try
{
m_workItem = workItem;
DocumentText dtCheck;
switch (workItem.Extension)
{
case "doc":
WordDocumentReader wrdRdr = new WordDocumentReader(workItem.BaseFileName);
try
{
dtCheck = wrdRdr.Read();
}
catch (Exception)
{
return; // failed to discover source document
}
CompareDiscoveryForDoc(workItem.BaseFileName, workItem.DiscoveredText, dtCheck);
break;
case "ppt":
PptDocumentReader pptRdr = new PptDocumentReader(workItem.BaseFileName);
try
{
dtCheck = pptRdr.Read();
}
catch (Exception)
{
return; // failed to discover source document
}
CompareDiscoveryForPpt(workItem.BaseFileName, workItem.DiscoveredText, dtCheck);
break;
case "xls":
ExcelDocumentReader xlsRdr = new ExcelDocumentReader(workItem.BaseFileName);
try
{
dtCheck = xlsRdr.Read();
}
catch (Exception)
{
return; // failed to discover source document
}
CompareDiscoveryForXls(workItem.BaseFileName, workItem.DiscoveredText, dtCheck);
break;
default:
throw new Exception("File extension not expected : " + workItem.Extension);
}
}
catch (Exception e)
{
workItem.FailureMode = FailureMode.DiscoveryMismatch;
throw e;
}
}
protected static IAbstractTextType GetDiscoveredTextType(string fileName, ContentType contentType)
{
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(TESTFILE_DIR + fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttresult = docText.GetUniqueTextType(contentType);
Assert.IsNotNull(ttresult, "we unexpectedly found no text of content type " + contentType.ToString());
return ttresult;
}
public void TestDiscoverSmallTextWithParaCharInteractionAndMultiPara_tc1()
{
string fileName = TESTFILE_DIR + "MultiParaSmallText_tracked_1.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttST = docText.GetUniqueTextType(ContentType.SmallText);
Assert.IsNotNull(ttST, "we unexpectedly found no small text");
Assert.AreEqual(1, ttST.Count, "Expected to get 1 separate small text items");
Assert.AreEqual("but this large", ttST.Nodes[0].GetInfo("Content")[0].value);
}
private void CleanFile(string fileName, List<ContentType> listContentTypes, List<Exclusion> listExclusion)
{
try
{
using (WordDocumentReader wrdReader = new WordDocumentReader(fileName, true))
{
wrdReader.Clean(listContentTypes, listExclusion);
}
}
catch (System.Exception ex)
{
Logger.LogError("Word Binary cleaning failed");
Logger.LogError(ex);
throw;
}
}
public void TestDiscoverSmallTextWithParaCharInteractionAndMultiPara()
{
string fileName = TESTFILE_DIR + "MultiParaSmallText.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttST = docText.GetUniqueTextType(ContentType.SmallText);
Assert.IsNotNull(ttST, "we unexpectedly found no hidden text");
Assert.AreEqual(4, ttST.Count, "Expected to get 4 separate small text items");
Assert.AreEqual("This is in small ", ttST.Nodes[0].GetInfo("Content")[0].value);
Assert.AreEqual(" and more small\r", ttST.Nodes[1].GetInfo("Content")[0].value);
Assert.AreEqual("An entirely small para\r", ttST.Nodes[2].GetInfo("Content")[0].value);
Assert.AreEqual("And another\r", ttST.Nodes[3].GetInfo("Content")[0].value);
}
public override bool VerifyFile(TempFileForActions tempFile)
{
try
{
using (WordDocumentReader reader = new WordDocumentReader(tempFile.TempFile, true))
{
reader.Read();
return true;
}
}
catch (System.Exception ex)
{
Logger.LogError("Word Verification failed");
Logger.LogError(ex);
}
return false;
}
public void TestDiscoverHiddenTextWithHierarchichalStyles()
{
string fileName = TESTFILE_DIR + "HierarchicalHiddenStyles.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttHT = docText.GetUniqueTextType(ContentType.HiddenText);
Assert.IsNotNull(ttHT, "we unexpectedly found no hidden text");
Assert.AreEqual(5, ttHT.Count, "Expected to get 5 separate hidden text items");
Assert.AreEqual("Hidden style\r", ttHT.Nodes[0].GetInfo("Content")[0].value);
Assert.AreEqual("Double opposite style\r", ttHT.Nodes[1].GetInfo("Content")[0].value);
Assert.AreEqual("HiddenChar style\r", ttHT.Nodes[2].GetInfo("Content")[0].value);
Assert.AreEqual("2Oppos ", ttHT.Nodes[3].GetInfo("Content")[0].value);
Assert.AreEqual(" hidden", ttHT.Nodes[4].GetInfo("Content")[0].value);
}
public void TestQuickDiscovery()
{
string fileName = TESTFILE_DIR + "Simple.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttHidden = docText.GetUniqueTextType(ContentType.HiddenText);
foreach (IAbstractTextNode tn in ttHidden)
{
foreach (NodeInfo ni in tn.GetInfo("Content"))
{
if (ni.value == "Some hidden text\r")
return;
}
}
Assert.Fail("Did not find expected hidden text");
}
public void TestDiscoverTableChanges()
{
string fileName = TESTFILE_DIR + "TestTableTCs.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttTC = docText.GetUniqueTextType(ContentType.TrackChange);
Assert.IsNotNull(ttTC, "we unexpectedly found no track changes");
Assert.AreEqual(7, ttTC.Count, "Expected to get 7 separate track change items");
Assert.AreEqual("Table Properties", ttTC.Nodes[1].GetInfo("Type")[0].value);
Assert.AreEqual("Table Properties", ttTC.Nodes[6].GetInfo("Type")[0].value);
}
public DocumentText DiscoverDocument(string sFilename)
{
switch (m_ft)
{
case Workshare.Policy.FileType.WordDocument:
using (WordDocumentReader Word2003Reader1 = new WordDocumentReader(sFilename, false))
{
return Word2003Reader1.Read();
}
case Workshare.Policy.FileType.ExcelSheet:
using (ExcelDocumentReader Excel2003Reader1 = new ExcelDocumentReader(sFilename, false))
{
return Excel2003Reader1.Read();
}
case Workshare.Policy.FileType.PowerPoint:
using (Workshare.FCS.Lite.PptDocumentReader Ppt2003Reader1 = new PptDocumentReader(sFilename, false))
{
return Ppt2003Reader1.Read();
}
default:
break;
}
return null;
}
public void TestDiscoverCharFormattingTCs()
{
string fileName = TESTFILE_DIR + "DiscoverCharTCs.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttTC = docText.GetUniqueTextType(ContentType.TrackChange);
Assert.IsNotNull(ttTC, "we unexpectedly found no track changes");
Assert.AreEqual(9, ttTC.Count, "Expected to get 9 separate track change items");
for (int i = 0; i < 9; i++)
{
Assert.AreEqual("Property", ttTC.Nodes[i].GetInfo("Type")[0].value);
}
}
public void DoBinaryClean(List<ContentType> listContentTypes)
{
switch (m_ft)
{
case Workshare.Policy.FileType.WordDocument:
using (WordDocumentReader Word2003Reader1 = new WordDocumentReader(m_filenameIn, true))
{
Word2003Reader1.Clean(listContentTypes);
}
break;
case Workshare.Policy.FileType.ExcelSheet:
using (ExcelDocumentReader Excel2003Reader1 = new ExcelDocumentReader(m_filenameIn, true))
{
Excel2003Reader1.Clean(listContentTypes);
}
break;
case Workshare.Policy.FileType.PowerPoint:
using (Workshare.FCS.Lite.PptDocumentReader Ppt2003Reader1 = new PptDocumentReader(m_filenameIn, true))
{
Ppt2003Reader1.Clean(listContentTypes);
}
break;
default:
break;
}
}
public void TestDiscoverListnumChanges()
{
string fileName = TESTFILE_DIR + "ChangesToListNums.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttTC = docText.GetUniqueTextType(ContentType.TrackChange);
Assert.IsNotNull(ttTC, "we unexpectedly found no track changes");
Assert.AreEqual(2, ttTC.Count, "Expected to get 2 separate track change items");
Assert.AreEqual("Insertion", ttTC.Nodes[0].GetInfo("Type")[0].value);
Assert.AreEqual("Workshare", ttTC.Nodes[0].GetInfo("Author")[0].value);
Assert.AreEqual("two and a half\r", ttTC.Nodes[0].GetInfo("Content")[0].value);
Assert.AreEqual("ListNumber", ttTC.Nodes[1].GetInfo("Type")[0].value);
Assert.AreEqual("Workshare", ttTC.Nodes[1].GetInfo("Author")[0].value);
Assert.AreEqual("two and a half\r", ttTC.Nodes[1].GetInfo("Content")[0].value);
}
/// <summary>
/// </summary>
/// <returns>A FCS.Lite.DocumentText object</returns>
public FCS.Lite.Base.DocumentText AdvancedRead()
{
if (m_docText == null)
{
FCS.Lite.Base.DocumentReader docReader;
switch (m_fileData.FileType)
{
case FileType.WordDocument:
docReader = new WordDocumentReader(m_fileData.BinaryFileData);
break;
case FileType.PowerPoint:
docReader = new PptDocumentReader(m_fileData.BinaryFileData);
break;
case FileType.ExcelSheet:
docReader = new ExcelDocumentReader(m_fileData.BinaryFileData);
break;
case FileType.WordDocumentX:
case FileType.WordDocumentMacroX:
case FileType.WordDocumentTemplateX:
case FileType.WordDocumentMacroTemplateX:
docReader = new DocxDocumentReader(m_fileData.BinaryFileData);
break;
case FileType.PowerPointX:
case FileType.PowerPointMacroX:
case FileType.PowerPointTemplateX:
case FileType.PowerPointMacroTemplateX:
case FileType.PowerPointShowX:
case FileType.PowerPointMacroShowX:
docReader = new PptxDocumentReader(m_fileData.BinaryFileData);
break;
case FileType.ExcelSheetX:
case FileType.ExcelSheetMacroX:
case FileType.ExcelSheetTemplateX:
case FileType.ExcelSheetMacroTemplateX:
docReader = new XlsxDocumentReader(m_fileData.BinaryFileData);
break;
case FileType.PDFDocument:
docReader = new PdfDocumentReader(m_fileData.BinaryFileData);
break;
default:
return m_docText;
}
using (docReader)
{
m_docText = docReader.Read();
}
}
return m_docText;
}
DocumentText DiscoverDocument(string sFilename)
{
switch (m_ft)
{
case Workshare.Policy.FileType.WordDocument:
using (WordDocumentReader Word2003Reader1 = new WordDocumentReader(sFilename, false))
{
return Word2003Reader1.Read();
}
case Workshare.Policy.FileType.ExcelSheet:
using (ExcelDocumentReader Excel2003Reader1 = new ExcelDocumentReader(sFilename, false))
{
return Excel2003Reader1.Read();
}
case Workshare.Policy.FileType.PowerPoint:
using (Workshare.FCS.Lite.PptDocumentReader Ppt2003Reader1 = new PptDocumentReader(sFilename, false))
{
return Ppt2003Reader1.Read();
}
case Workshare.Policy.FileType.WordDocumentX:
case Workshare.Policy.FileType.WordDocumentMacroX:
case Workshare.Policy.FileType.WordDocumentTemplateX:
case Workshare.Policy.FileType.WordDocumentMacroTemplateX:
using (DocxDocumentReader Word2007Reader1 = new DocxDocumentReader(sFilename))
{
return Word2007Reader1.Read();
}
case Workshare.Policy.FileType.ExcelSheetX:
case Workshare.Policy.FileType.ExcelSheetMacroX:
case Workshare.Policy.FileType.ExcelSheetTemplateX:
case Workshare.Policy.FileType.ExcelSheetMacroTemplateX:
using (XlsxDocumentReader Excel2007Reader1 = new XlsxDocumentReader(sFilename))
{
return Excel2007Reader1.Read();
}
case Workshare.Policy.FileType.PowerPointX:
case Workshare.Policy.FileType.PowerPointMacroX:
case Workshare.Policy.FileType.PowerPointTemplateX:
case Workshare.Policy.FileType.PowerPointMacroTemplateX:
case Workshare.Policy.FileType.PowerPointShowX:
case Workshare.Policy.FileType.PowerPointMacroShowX:
using (PptxDocumentReader Ppt2007Reader1 = new PptxDocumentReader(sFilename))
{
return Ppt2007Reader1.Read();
}
default:
break;
}
return null;
}
public void TestDontDiscoverListNumTCsWhereTheyDontExist()
{
string fileName = TESTFILE_DIR + "AppSpec.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttTC = docText.GetUniqueTextType(ContentType.TrackChange);
if (ttTC == null)
return; // all well
Assert.AreEqual(0, ttTC.Count, "Expected to get no track change items");
}
/// <summary>
/// Original incarnation of lightspeed clean method. Left for comparison. There is at least one document that gets corrupted by the
/// lightspeed clean user action as opposed to the method below. see Rally DE8912 in Professional & Deltaview project.
/// </summary>
/// <param name="listContentTypes"></param>
private void DoLightSpeedClean(List<ContentType> listContentTypes)
{
System.Diagnostics.Stopwatch watch = new System.Diagnostics.Stopwatch();
watch.Start();
switch (m_ft)
{
case Workshare.Policy.FileType.WordDocument:
using (WordDocumentReader Word2003Reader1 = new WordDocumentReader(m_sFileForBinClean, true))
{
Word2003Reader1.Clean(listContentTypes);
}
break;
case Workshare.Policy.FileType.ExcelSheet:
using (ExcelDocumentReader Excel2003Reader1 = new ExcelDocumentReader(m_sFileForBinClean, true))
{
Excel2003Reader1.Clean(listContentTypes);
}
break;
case Workshare.Policy.FileType.PowerPoint:
using (Workshare.FCS.Lite.PptDocumentReader Ppt2003Reader1 = new PptDocumentReader(m_sFileForBinClean, true))
{
Ppt2003Reader1.Clean(listContentTypes);
}
break;
case Workshare.Policy.FileType.WordDocumentX:
case Workshare.Policy.FileType.WordDocumentMacroX:
case Workshare.Policy.FileType.WordDocumentTemplateX:
case Workshare.Policy.FileType.WordDocumentMacroTemplateX:
{
string outFileName = System.IO.Path.GetTempFileName();
using (DocxDocumentReader Word2007Reader1 = new DocxDocumentReader(m_sFileForBinClean))
{
using (Stream outStr = File.Open(outFileName, FileMode.Create))
{
Word2007Reader1.CleanTo(outStr, listContentTypes);
}
}
File.Copy(outFileName, m_sFileForBinClean, true);
File.Delete(outFileName);
break;
}
case Workshare.Policy.FileType.ExcelSheetX:
case Workshare.Policy.FileType.ExcelSheetMacroX:
case Workshare.Policy.FileType.ExcelSheetTemplateX:
case Workshare.Policy.FileType.ExcelSheetMacroTemplateX:
{
string outFileName = System.IO.Path.GetTempFileName();
using (XlsxDocumentReader Excel2007Reader1 = new XlsxDocumentReader(m_sFileForBinClean))
{
using (Stream outStr = File.Open(outFileName, FileMode.Create))
{
Excel2007Reader1.CleanTo(outStr, listContentTypes);
}
}
File.Copy(outFileName, m_sFileForBinClean, true);
File.Delete(outFileName);
break;
}
case Workshare.Policy.FileType.PowerPointX:
case Workshare.Policy.FileType.PowerPointMacroX:
case Workshare.Policy.FileType.PowerPointTemplateX:
case Workshare.Policy.FileType.PowerPointMacroTemplateX:
case Workshare.Policy.FileType.PowerPointShowX:
case Workshare.Policy.FileType.PowerPointMacroShowX:
{
string outFileName = System.IO.Path.GetTempFileName();
using (PptxDocumentReader Ppt2007Reader1 = new PptxDocumentReader(m_sFileForBinClean))
{
using (Stream outStr = File.Open(outFileName, FileMode.Create))
{
Ppt2007Reader1.CleanTo(outStr, listContentTypes);
}
}
File.Copy(outFileName, m_sFileForBinClean, true);
File.Delete(outFileName);
break;
}
default:
break;
}
watch.Stop();
m_binCleanTime = watch.Elapsed.TotalSeconds;
}
public void TestDiscover2TableChangesInSameTable()
{
string fileName = TESTFILE_DIR + "2TableTCsInOneTable.doc";
Workshare.FCS.Lite.WordDocumentReader docReader = new WordDocumentReader(fileName);
DocumentText docText = docReader.Read();
IAbstractTextType ttTC = docText.GetUniqueTextType(ContentType.TrackChange);
Assert.IsNotNull(ttTC, "we unexpectedly found no track changes");
Assert.AreEqual(2, ttTC.Count, "Expected to get 2 separate track change items");
foreach (IAbstractTextNode node in ttTC.Nodes)
{
Assert.AreEqual("Table Properties", node.GetInfo("Type")[0].value);
}
}
